Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3993 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1058724 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2265. Min Act: -0.0000

Data Index: 307163 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1834007 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2112. Min Act: -0.0000

Data Index: 941975 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2076. Min Act: -0.0000

Data Index: 214472 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1881435 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2003. Min Act: -0.0000

Data Index: 151976 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1120045 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2030. Min Act: -0.0000

Data Index: 50746 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1897. Min Act: -0.0000

Data Index: 742107 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1416910 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1834. Min Act: -0.0000

Data Index: 171815 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1628575 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1834. Min Act: -0.0000

Data Index: 57729 (The Pile)

Max Activating Token Index: 504

Text #14

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1895. Min Act: -0.0000

Data Index: 157318 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1339904 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1009716 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1099593 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1897182 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1676. Min Act: -0.0000

Data Index: 181069 (The Pile)

Max Activating Token Index: 162